Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), but the description adds meaningful behavior beyond them: duplicates refused within the same narrative/raising Scan, creation is not exactly-once, retry recovery guidance ('inspect the board before retrying'), and that later Scans track its standing like a Scan-raised one. This is unusually rich, though return semantics are left to the output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core purpose, then sequences prerequisites, authoring fields, and caveats. Dense but each sentence carries information. Slightly long and a few clauses could be tightened, but nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 13 params, a nested seed object, and an existing output schema (so returns needn't be explained), the description covers creation stage, seeding, validation constraints, duplicate behavior, and prerequisites. The remaining gap is that several optional enum params are neither described here nor in the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 54% across 13 params, so the description must compensate. It defines the three core content fields (title, question, whatToDo), clarifies that why:null/pagesToFix:null initialize empty content, and states that any seed must exist on this Site/Topic. It leaves effort/impact/intent/confidence/targetStanding semantics largely to the schema, so it adds value but not full compensation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Raises a new recommendation the Scan did not') and immediately distinguishes it from Scan-raised and other recommendation siblings by scope — user-initiated activities. An agent can tell this apart from edit_recommendation/create_recommendation_note without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit prerequisites (existing completed Scan; narrativeId from get_narratives), a required approach ('ground the brief in that narrative first with get_narrative_claims and get_prompt_results'), a confirmation step with the user, and an exclusion ('a baseline with baselineMeasured=false is unmeasured, not evidence of AI omission'). Names the supporting read tools to call first.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.